{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:7CUTVHLU2OVF6ED323N7NTB3HK","short_pith_number":"pith:7CUTVHLU","schema_version":"1.0","canonical_sha256":"f8a93a9d74d3aa5f107bd6dbf6cc3b3a8a286e1acab85a98daf505bc49bb1b2f","source":{"kind":"arxiv","id":"1204.3968","version":1},"attestation_state":"computed","paper":{"title":"Convolutional Neural Networks Applied to House Numbers Digit Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Pierre Sermanet, Soumith Chintala, Yann LeCun","submitted_at":"2012-04-18T03:48:38Z","abstract_excerpt":"We classify digits of real-world house numbers using convolutional neural networks (ConvNets). ConvNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 94.85% accuracy on the SVHN dataset (45.2% error improvement). Furthermore, we analyze the benefits of differ"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1204.3968","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2012-04-18T03:48:38Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"52ce4b2945dcf0d1c047fd994cab94861f014b1e3e603885a3a352e369a5863b","abstract_canon_sha256":"59468892116001df53f1c235d5d145e5eb266bb64a6604dd77ace44505ea6f53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:57:38.144419Z","signature_b64":"Uwr/9UXZqXzzDBJTkOhaE1u9UjOU05bnbF12TJ4/drTMCcDVaZm//kduE9fXc4D7JuXJaaaMUt/sUC2AJOKTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8a93a9d74d3aa5f107bd6dbf6cc3b3a8a286e1acab85a98daf505bc49bb1b2f","last_reissued_at":"2026-05-18T03:57:38.143774Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:57:38.143774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional Neural Networks Applied to House Numbers Digit Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Pierre Sermanet, Soumith Chintala, Yann LeCun","submitted_at":"2012-04-18T03:48:38Z","abstract_excerpt":"We classify digits of real-world house numbers using convolutional neural networks (ConvNets). ConvNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 94.85% accuracy on the SVHN dataset (45.2% error improvement). Furthermore, we analyze the benefits of differ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1204.3968","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1204.3968","created_at":"2026-05-18T03:57:38.143889+00:00"},{"alias_kind":"arxiv_version","alias_value":"1204.3968v1","created_at":"2026-05-18T03:57:38.143889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1204.3968","created_at":"2026-05-18T03:57:38.143889+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CUTVHLU2OVF","created_at":"2026-05-18T12:26:56.085431+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CUTVHLU2OVF6ED3","created_at":"2026-05-18T12:26:56.085431+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CUTVHLU","created_at":"2026-05-18T12:26:56.085431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CUTVHLU2OVF6ED323N7NTB3HK","json":"https://pith.science/pith/7CUTVHLU2OVF6ED323N7NTB3HK.json","graph_json":"https://pith.science/api/pith-number/7CUTVHLU2OVF6ED323N7NTB3HK/graph.json","events_json":"https://pith.science/api/pith-number/7CUTVHLU2OVF6ED323N7NTB3HK/events.json","paper":"https://pith.science/paper/7CUTVHLU"},"agent_actions":{"view_html":"https://pith.science/pith/7CUTVHLU2OVF6ED323N7NTB3HK","download_json":"https://pith.science/pith/7CUTVHLU2OVF6ED323N7NTB3HK.json","view_paper":"https://pith.science/paper/7CUTVHLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1204.3968&json=true","fetch_graph":"https://pith.science/api/pith-number/7CUTVHLU2OVF6ED323N7NTB3HK/graph.json","fetch_events":"https://pith.science/api/pith-number/7CUTVHLU2OVF6ED323N7NTB3HK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CUTVHLU2OVF6ED323N7NTB3HK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CUTVHLU2OVF6ED323N7NTB3HK/action/storage_attestation","attest_author":"https://pith.science/pith/7CUTVHLU2OVF6ED323N7NTB3HK/action/author_attestation","sign_citation":"https://pith.science/pith/7CUTVHLU2OVF6ED323N7NTB3HK/action/citation_signature","submit_replication":"https://pith.science/pith/7CUTVHLU2OVF6ED323N7NTB3HK/action/replication_record"}},"created_at":"2026-05-18T03:57:38.143889+00:00","updated_at":"2026-05-18T03:57:38.143889+00:00"}